Tang Guoling, Han Yaning, Sun Xing, Zhang Ruonan, Han Ming-Hu, Liu Quanying, Wei Pengfei
University of Chinese Academy of Sciences, Shenzhen, China.
University of Chinese Academy of Sciences, Beijing, China.
Elife. 2025 May 6;13:RP95709. doi: 10.7554/eLife.95709.
Deep learning-based methods have advanced animal pose estimation, enhancing accuracy, and efficiency in quantifying animal behavior. However, these methods frequently experience tracking drift, where noise-induced jumps in body point estimates compromise reliability. Here, we present the anti-drift pose tracker (ADPT), a transformer-based tool that mitigates tracking drift in behavioral analysis. Extensive experiments across cross-species datasets-including proprietary mouse and monkey recordings and public and macaque datasets-demonstrate that ADPT significantly reduces drift and surpasses existing models like DeepLabCut and SLEAP in accuracy. Moreover, ADPT achieved 93.16% identification accuracy for 10 unmarked mice and 90.36% accuracy for freely interacting unmarked mice, which can be further refined to 99.72%, enhancing both anti-drift performance and pose estimation accuracy in social interactions. With its end-to-end design, ADPT is computationally efficient and suitable for real-time analysis, offering a robust solution for reproducible animal behavior studies. The ADPT code is available at https://github.com/tangguoling/ADPT.
基于深度学习的方法推动了动物姿态估计的发展，提高了在量化动物行为方面的准确性和效率。然而，这些方法经常出现跟踪漂移问题，即噪声引起的身体关键点估计跳跃会损害可靠性。在此，我们提出了抗漂移姿态跟踪器（ADPT），这是一种基于Transformer的工具，可减轻行为分析中的跟踪漂移。在跨物种数据集上进行的大量实验——包括专有的小鼠和猴子记录以及公开的猕猴数据集——表明，ADPT显著减少了漂移，并且在准确性方面超过了DeepLabCut和SLEAP等现有模型。此外，ADPT对10只未标记小鼠的识别准确率达到93.16%，对自由互动的未标记小鼠的准确率达到90.36%，这一准确率可进一步提高到99.72%，在社交互动中提高了抗漂移性能和姿态估计准确性。凭借其端到端设计，ADPT计算效率高，适用于实时分析，为可重复的动物行为研究提供了一个强大的解决方案。ADPT代码可在https://github.com/tangguoling/ADPT获取。
